© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27691
    Prev
    Next
    INDEX
    Explanations

    occurrences of SQL table creation statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    111
    +0.11
    0.6%
    389
    +0.11
    0.6%
    61
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.11
    0.01
    389
    +0.11
    0.01
    61
    +0.10
    0.01
    Negative Logits
    upon
    -1.74
    iento
    -1.71
    ociation
    -1.57
    oles
    -1.52
    jen
    -1.44
    ancel
    -1.43
    dll
    -1.37
     appropriate
    -1.37
    ativity
    -1.36
      ↵
    -1.33
    POSITIVE LOGITS
    roads
    1.62
    iffs
    1.52
    lists
    1.48
    rex
    1.47
     Bay
    1.46
    rams
    1.44
     alia
    1.43
    orse
    1.42
    forge
    1.41
    aines
    1.40
    Activations Density 0.047%

    No Known Activations